# Alpha Berkeley Framework
> **🚧 Early Access Release**
> This is an early access version of the Alpha Berkeley Framework. While the core functionality is stable and ready for experimentation, documentation and APIs may still evolve. We welcome feedback and contributions!
An open-source, domain-agnostic, capability-based architecture for building intelligent agents that can be adapted to any specific domain.
**📄 Research**
This work was presented as a contributed oral presentation at [ICALEPCS'25](https://indico.jacow.org/event/86/overview) and will be featured at the [Machine Learning and the Physical Sciences Workshop](https://ml4physicalsciences.github.io/2025/) at NeurIPS 2025.
## 🚀 Quick Start
```bash
# Install the framework
pip install alpha-berkeley-framework
# Create a new project from a template
framework init my-weather-agent --template hello_world_weather
# Navigate to your project
cd my-weather-agent
# Setup environment
cp .env.example .env
# Edit .env with your API keys
# Start the command line chat interface
framework chat
# Or use the web interface at http://localhost:8080
```
## 📚 Documentation
**[📖 Read the Full Documentation →](https://thellert.github.io/alpha_berkeley)**
## Key Features
- **Scalable Capability Management** - Efficiently scales to large sets of specialized agents
- **Structured Orchestration** - Converts freeform inputs into clear, executable plans
- **Modular Architecture** - Easily integrates new capabilities without disrupting workflows
- **Human-in-the-Loop Ready** - Transparent execution plans for inspection and debugging
- **Domain-Adaptable** - Designed for heterogeneous scientific infrastructure
---
## 📖 Citation
If you use the Alpha Berkeley Framework in your research or projects, please cite our [paper](https://arxiv.org/abs/2508.15066):
```bibtex
@misc{hellert2025alphaberkeley,
title={Alpha Berkeley: A Scalable Framework for the Orchestration of Agentic Systems},
author={Thorsten Hellert and João Montenegro and Antonin Sulc},
year={2025},
eprint={2508.15066},
archivePrefix={arXiv},
primaryClass={cs.MA},
url={https://arxiv.org/abs/2508.15066},
}
```
---
*For detailed installation instructions, tutorials, and API reference, please visit our [complete documentation](https://thellert.github.io/alpha_berkeley).*
---
**Copyright Notice**
Alpha Berkeley Framework (alpha berkeley) Copyright (c) 2025, The Regents of the University of California, through Lawrence Berkeley National Laboratory (subject to receipt of any required approvals from the U.S. Dept. of Energy). All rights reserved.
If you have questions about your rights to use or distribute this software,
please contact Berkeley Lab's Intellectual Property Office at
IPO@lbl.gov.
NOTICE. This Software was developed under funding from the U.S. Department
of Energy and the U.S. Government consequently retains certain rights. As
such, the U.S. Government has been granted for itself and others acting on
its behalf a paid-up, nonexclusive, irrevocable, worldwide license in the
Software to reproduce, distribute copies to the public, prepare derivative
works, and perform publicly and display publicly, and to permit others to do so.
---
Raw data
{
"_id": null,
"home_page": null,
"name": "alpha-berkeley-framework",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.11",
"maintainer_email": "Thorsten Hellert <thellert@lbl.gov>",
"keywords": "ai, agents, framework, scientific-computing, langgraph, epics, accelerator-physics, als, berkeley, agent-framework, capability-based, human-in-the-loop, container-orchestration",
"author": null,
"author_email": "Thorsten Hellert <thellert@lbl.gov>",
"download_url": "https://files.pythonhosted.org/packages/f4/1a/2af38e42021020b81f7090f265b0c96d667feeb41d8174d31660e908dd74/alpha_berkeley_framework-0.7.5.tar.gz",
"platform": null,
"description": "# Alpha Berkeley Framework\n\n\n> **\ud83d\udea7 Early Access Release** \n> This is an early access version of the Alpha Berkeley Framework. While the core functionality is stable and ready for experimentation, documentation and APIs may still evolve. We welcome feedback and contributions!\n\nAn open-source, domain-agnostic, capability-based architecture for building intelligent agents that can be adapted to any specific domain.\n\n**\ud83d\udcc4 Research** \nThis work was presented as a contributed oral presentation at [ICALEPCS'25](https://indico.jacow.org/event/86/overview) and will be featured at the [Machine Learning and the Physical Sciences Workshop](https://ml4physicalsciences.github.io/2025/) at NeurIPS 2025.\n\n\n## \ud83d\ude80 Quick Start\n\n```bash\n# Install the framework\npip install alpha-berkeley-framework\n\n# Create a new project from a template\nframework init my-weather-agent --template hello_world_weather\n\n# Navigate to your project\ncd my-weather-agent\n\n# Setup environment\ncp .env.example .env\n# Edit .env with your API keys\n\n# Start the command line chat interface\nframework chat\n\n# Or use the web interface at http://localhost:8080\n```\n\n\n## \ud83d\udcda Documentation\n\n**[\ud83d\udcd6 Read the Full Documentation \u2192](https://thellert.github.io/alpha_berkeley)**\n\n\n## Key Features\n\n- **Scalable Capability Management** - Efficiently scales to large sets of specialized agents\n- **Structured Orchestration** - Converts freeform inputs into clear, executable plans\n- **Modular Architecture** - Easily integrates new capabilities without disrupting workflows\n- **Human-in-the-Loop Ready** - Transparent execution plans for inspection and debugging\n- **Domain-Adaptable** - Designed for heterogeneous scientific infrastructure\n\n---\n\n## \ud83d\udcd6 Citation\n\nIf you use the Alpha Berkeley Framework in your research or projects, please cite our [paper](https://arxiv.org/abs/2508.15066):\n\n```bibtex\n@misc{hellert2025alphaberkeley,\n title={Alpha Berkeley: A Scalable Framework for the Orchestration of Agentic Systems}, \n author={Thorsten Hellert and Jo\u00e3o Montenegro and Antonin Sulc},\n year={2025},\n eprint={2508.15066},\n archivePrefix={arXiv},\n primaryClass={cs.MA},\n url={https://arxiv.org/abs/2508.15066}, \n}\n```\n\n---\n\n*For detailed installation instructions, tutorials, and API reference, please visit our [complete documentation](https://thellert.github.io/alpha_berkeley).*\n\n---\n\n**Copyright Notice**\n\nAlpha Berkeley Framework (alpha berkeley) Copyright (c) 2025, The Regents of the University of California, through Lawrence Berkeley National Laboratory (subject to receipt of any required approvals from the U.S. Dept. of Energy). All rights reserved.\n\nIf you have questions about your rights to use or distribute this software,\nplease contact Berkeley Lab's Intellectual Property Office at\nIPO@lbl.gov.\n\nNOTICE. This Software was developed under funding from the U.S. Department\nof Energy and the U.S. Government consequently retains certain rights. As\nsuch, the U.S. Government has been granted for itself and others acting on\nits behalf a paid-up, nonexclusive, irrevocable, worldwide license in the\nSoftware to reproduce, distribute copies to the public, prepare derivative \nworks, and perform publicly and display publicly, and to permit others to do so.\n\n---\n",
"bugtrack_url": null,
"license": "BSD-3-Clause",
"summary": "An open-source, domain-agnostic, capability-based architecture for building intelligent agents",
"version": "0.7.5",
"project_urls": {
"Changelog": "https://github.com/thellert/alpha_berkeley/blob/main/CHANGELOG.md",
"Documentation": "https://thellert.github.io/alpha_berkeley",
"Homepage": "https://thellert.github.io/alpha_berkeley",
"Issues": "https://github.com/thellert/alpha_berkeley/issues",
"Paper": "https://arxiv.org/abs/2508.15066",
"Repository": "https://github.com/thellert/alpha_berkeley"
},
"split_keywords": [
"ai",
" agents",
" framework",
" scientific-computing",
" langgraph",
" epics",
" accelerator-physics",
" als",
" berkeley",
" agent-framework",
" capability-based",
" human-in-the-loop",
" container-orchestration"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "e9326d781282169e0074203cf336069cf63c859b89e9af47b8f7beadbcef761e",
"md5": "bcb57fb1b1353a3f938bece2d4a90fef",
"sha256": "b6c7ce0c4ee14503fce74506a33a4b5ddc4a9f4c371cb5d403f1412742a8e6cf"
},
"downloads": -1,
"filename": "alpha_berkeley_framework-0.7.5-py3-none-any.whl",
"has_sig": false,
"md5_digest": "bcb57fb1b1353a3f938bece2d4a90fef",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.11",
"size": 1405735,
"upload_time": "2025-10-28T20:24:19",
"upload_time_iso_8601": "2025-10-28T20:24:19.813877Z",
"url": "https://files.pythonhosted.org/packages/e9/32/6d781282169e0074203cf336069cf63c859b89e9af47b8f7beadbcef761e/alpha_berkeley_framework-0.7.5-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "f41a2af38e42021020b81f7090f265b0c96d667feeb41d8174d31660e908dd74",
"md5": "59fbf2525617942eabb56d4ac5cd053f",
"sha256": "1a8d6754b9c0759932d727137f69c1bce7697a7d62f8c2b389fcf83ca2b7f903"
},
"downloads": -1,
"filename": "alpha_berkeley_framework-0.7.5.tar.gz",
"has_sig": false,
"md5_digest": "59fbf2525617942eabb56d4ac5cd053f",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.11",
"size": 1314420,
"upload_time": "2025-10-28T20:24:21",
"upload_time_iso_8601": "2025-10-28T20:24:21.152159Z",
"url": "https://files.pythonhosted.org/packages/f4/1a/2af38e42021020b81f7090f265b0c96d667feeb41d8174d31660e908dd74/alpha_berkeley_framework-0.7.5.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-28 20:24:21",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "thellert",
"github_project": "alpha_berkeley",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "alpha-berkeley-framework"
}
JSON
